How to beginner · 4 min read

How to use Mistral with OpenAI SDK

Q: How to use Mistral with OpenAI SDK

Use the OpenAI Python SDK with the base_url set to Mistral's API endpoint and your Mistral API key from os.environ. Call client.chat.completions.create with the desired mistral-large-latest or other Mistral model and your chat messages.

Quick answer

Use the OpenAI Python SDK with the base_url set to Mistral's API endpoint and your Mistral API key from os.environ. Call client.chat.completions.create with the desired mistral-large-latest or other Mistral model and your chat messages.

PREREQUISITES

Python 3.8+
Mistral API key
pip install openai>=1.0

Setup

Install the openai Python package version 1.0 or higher. Set your Mistral API key as an environment variable MISTRAL_API_KEY before running the code.

bash

pip install openai>=1.0

Step by step

This example shows how to create a chat completion request to Mistral's mistral-large-latest model using the OpenAI SDK with the base_url override.

python

import os
from openai import OpenAI

client = OpenAI(api_key=os.environ["MISTRAL_API_KEY"], base_url="https://api.mistral.ai/v1")

response = client.chat.completions.create(
    model="mistral-large-latest",
    messages=[{"role": "user", "content": "Hello, how can I use Mistral with OpenAI SDK?"}]
)

print(response.choices[0].message.content)

output

Hello! You can use the OpenAI SDK by setting the base_url to Mistral's API endpoint and specifying a Mistral model like "mistral-large-latest" in your chat completion requests.

Common variations

Use different Mistral models such as mistral-small-latest or codestral-latest by changing the model parameter.
For asynchronous calls, use Python's asyncio with the OpenAI SDK's async methods.
Streaming responses are supported by passing stream=True to chat.completions.create.

python

import asyncio
from openai import OpenAI

async def async_chat():
    client = OpenAI(api_key=os.environ["MISTRAL_API_KEY"], base_url="https://api.mistral.ai/v1")
    response = await client.chat.completions.acreate(
        model="mistral-large-latest",
        messages=[{"role": "user", "content": "Stream a response from Mistral."}],
        stream=True
    )
    async for chunk in response:
        print(chunk.choices[0].delta.get("content", ""), end="")

asyncio.run(async_chat())

output

Streaming response text from Mistral appears here in real time...

Troubleshooting

If you get authentication errors, verify your MISTRAL_API_KEY environment variable is set correctly.
Ensure the base_url is exactly https://api.mistral.ai/v1 to avoid endpoint errors.
Check your network connectivity if requests time out.

✅

Key Takeaways

Set base_url to https://api.mistral.ai/v1 when using Mistral with OpenAI SDK.
Use environment variables for your Mistral API key to keep credentials secure.
The OpenAI SDK supports async and streaming with Mistral models.
Switch models by changing the model parameter in your requests.

Verified 2026-04 · mistral-large-latest, mistral-small-latest, codestral-latest

Verify ↗